专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08391963B2 Use of machine learning for classification of magneto cardiograms 有权
公开(公告)号：US08391963B2
公开(公告)日：2013-03-05
申请号：US12819095
申请日：2010-06-18
申请人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
发明人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
IPC分类号： A61B5/04
CPC分类号： A61B5/7267 , A61B5/04007 , A61B5/7203 , A61B5/7253 , A61B5/726 , A61B2560/0475 , G06K9/00496 , G06K9/00523 , G06N3/086 , G16H50/20
摘要： The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.

2. 发明授权

US08527435B1 Sigma tuning of gaussian kernels: detection of ischemia from magnetocardiograms 有权
标题翻译：高斯核的Sigma调整：从心电图检测缺血
公开(公告)号：US08527435B1
公开(公告)日：2013-09-03
申请号：US13181734
申请日：2011-07-13
申请人： Long Han , Mark Embrechts , Boleslaw Szymanski , Karsten Sternickel , Alexander Ross
发明人： Long Han , Mark Embrechts , Boleslaw Szymanski , Karsten Sternickel , Alexander Ross
IPC分类号： G06F15/18 , G06G7/48 , A61B5/04
CPC分类号： A61B5/7267 , A61B5/04007 , G06K9/00496 , G06K9/00523 , G06K9/6273 , G06N3/086 , G06N99/005 , G16H50/20
摘要： A novel Levenberg-Marquardt like second-order algorithm for tuning the Parzen window σ in a Radial Basis Function (Gaussian) kernel. Each attribute has its own sigma parameter. The values of the optimized σ are then used as a gauge for variable selection. Kernel Partial Least Squares (K-PLS) model is applied to several benchmark data sets to estimate effectiveness of second-order sigma tuning procedure for an RBF kernel. The variable subset selection method based on these sigma values is then compared with different feature selection procedures such as random forests and sensitivity analysis. The sigma-tuned RBF kernel model outperforms K-PLS and SVM models with a single sigma value. K-PLS models also compare favorably with Least Squares Support Vector Machines (LS-SVM), epsilon-insensitive Support Vector Regression and traditional PLS. Sigma tuning and variable selection is applied to industrial magnetocardiograph data for detection of ischemic heart disease from measurement of magnetic field around the heart.
摘要翻译：一种新颖的Levenberg-Marquardt，如二阶算法，用于调整径向基函数（高斯）内核中的Parzen窗口西格玛。每个属性都有自己的sigma参数。然后将优化的西格玛的值用作变量选择的量规。内核部分最小二乘法（K-PLS）模型应用于几个基准数据集，以估计RBF内核的二阶Σ调整过程的有效性。然后将基于这些西格玛值的可变子集选择方法与随机森林和敏感性分析等不同特征选择程序进行比较。西格玛调整的RBF内核模型优于具有单个西格玛值的K-PLS和SVM模型。 K-PLS模型也与最小二乘支持向量机（LS-SVM），ε不敏感支持向量回归和传统PLS相比较。 Sigma调整和可变选择应用于工业磁心图数据，用于通过测量心脏周围的磁场来检测缺血性心脏病。

3. 发明申请

US20110047105A1 Use of Machine Learning for Classification of Magneto Cardiograms 有权
标题翻译：使用机器学习分类磁心图
公开(公告)号：US20110047105A1
公开(公告)日：2011-02-24
申请号：US12819095
申请日：2010-06-18
申请人： Karsten Sternickel , Mark J. Embrechts , Boleslaw Szymanski
发明人： Karsten Sternickel , Mark J. Embrechts , Boleslaw Szymanski
IPC分类号： G06F15/18
CPC分类号： A61B5/7267 , A61B5/04007 , A61B5/7203 , A61B5/7253 , A61B5/726 , A61B2560/0475 , G06K9/00496 , G06K9/00523 , G06N3/086 , G16H50/20
摘要： The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.
摘要翻译：本文公开了在测量由心脏的电生理活性发出的磁场的磁心动图（MCG）中使用机器学习用于模式识别。直接内核方法用于将异常MCG心脏模式与正常心脏模式分离。对于无监督学习，引入了基于直接内核的自组织映射。对于监督学习，使用直接内核部分最小二乘法和（直接）内核岭回归。然后将这些结果与经典支持向量机和内核部分最小二乘法进行比较。这些方法的超参数在测试前对训练数据的验证子集进行调整。还进行了调查，最有效的预处理，使用局部，垂直，水平和二维（全局）Mahanalobis缩放，小波变换和通过过滤的变量选择。

4. 发明申请

US20070167846A1 Use of machine learning for classification of magneto cardiograms 失效
标题翻译：使用机器学习分类磁心电图
公开(公告)号：US20070167846A1
公开(公告)日：2007-07-19
申请号：US10561285
申请日：2004-07-01
申请人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
发明人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
IPC分类号： A61B5/04
CPC分类号： A61B5/7267 , A61B5/04007 , A61B5/7203 , A61B5/7253 , A61B5/726 , A61B2560/0475 , G06K9/00496 , G06K9/00523 , G06N3/086 , G16H50/20
摘要： The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering. The results, similar for all three methods, were encouraging, exceeding the quality of classification achieved by the trained experts. Thus, a device and associated method for classifying cardiography data is disclosed, comprising applying a kernel transform to sensed data acquired from sensors sensing electromagnetic heart activity, resulting in transformed data, prior to classifying the transformed data using machine learning.
摘要翻译：本文公开了在测量由心脏的电生理活性发出的磁场的磁心动图（MCG）中使用机器学习用于模式识别。直接内核方法用于将异常MCG心脏模式与正常心脏模式分离。对于无监督学习，引入了基于直接内核的自组织映射。对于监督学习，使用直接内核部分最小二乘法和（直接）内核岭回归。然后将这些结果与经典支持向量机和内核部分最小二乘法进行比较。这些方法的超参数在测试前对训练数据的验证子集进行调整。还进行了调查，最有效的预处理，使用局部，垂直，水平和二维（全局）Mahanalobis缩放，小波变换和通过过滤的变量选择。所有这三种方法类似的结果令人鼓舞，超出了受过培训的专家所实现的分类质量。因此，公开了一种用于分类心电图数据的装置和相关联的方法，包括：在使用机器学习分类变换的数据之前，将核心变换应用于从感测电磁心脏活动的传感器获取的感测数据，导致变换数据。

5. 发明申请

US20060149524A1 Network Management and control using collaborative on-line simulation 有权
标题翻译：使用协同在线仿真的网络管理和控制
公开(公告)号：US20060149524A1
公开(公告)日：2006-07-06
申请号：US10149207
申请日：2000-12-15
申请人： Shivkumar Kalyanaraman , Boleslaw Szymanski , Kenneth Vastola , Ye Tao , David Harrison , Bin Mo , Biplab Sikdar , Jingjie Jiang
发明人： Shivkumar Kalyanaraman , Boleslaw Szymanski , Kenneth Vastola , Ye Tao , David Harrison , Bin Mo , Biplab Sikdar , Jingjie Jiang
IPC分类号： G06F17/50
CPC分类号： H04L41/0816 , G06F17/5022 , G06F2217/04 , H04L41/142 , H04L41/145 , H04L43/00 , Y10S707/99932
摘要： A collaborative on-line simulation system and method to provide automated and pro-active control functions for computer network. In a wide area network, clients communicate through one or several nodes (108). Each node (108) contains routers which include control plane (202) and data plane (204). Collaborative on-line simulators (206) are interfaced to the network nodes (108) and continuously monitor the surrounding network conditions, communicate with other simulators and execute collaborative on-line simulation. Based on the simulation results, the on-line simulators (206) continuously tune selected network parameters to a more efficient operation point to fit the current network conditions.
摘要翻译：一种协作的在线仿真系统和方法，为计算机网络提供自动化和主动的控制功能。在广域网中，客户端通过一个或多个节点进行通信（108）。每个节点（108）包含包括控制平面（202）和数据平面（204）的路由器。协作在线模拟器（206）与网络节点（108）相连，并连续监测周围的网络状况，与其他模拟器通信并执行协同在线仿真。基于模拟结果，在线模拟器（206）将所选择的网络参数连续地调谐到更有效的操作点以适应当前网络条件。

6. 发明授权

US07742806B2 Use of machine learning for classification of magneto cardiograms 失效
标题翻译：使用机器学习分类磁心电图
公开(公告)号：US07742806B2
公开(公告)日：2010-06-22
申请号：US10561285
申请日：2004-07-01
申请人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
发明人： Karsten Sternickel , Boleslaw Szymanski , Mark Embrechts
IPC分类号： A61B5/04
CPC分类号： A61B5/7267 , A61B5/04007 , A61B5/7203 , A61B5/7253 , A61B5/726 , A61B2560/0475 , G06K9/00496 , G06K9/00523 , G06N3/086 , G16H50/20
摘要： The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering. The results, similar for all three methods, were encouraging, exceeding the quality of classification achieved by the trained experts. Thus, a device and associated method for classifying cardiography data is disclosed, comprising applying a kernel transform to sensed data acquired from sensors sensing electromagnetic heart activity, resulting in transformed data, prior to classifying the transformed data using machine learning.
摘要翻译：本文公开了在测量由心脏的电生理活性发出的磁场的磁心动图（MCG）中使用机器学习用于模式识别。直接内核方法用于将异常MCG心脏模式与正常心脏模式分离。对于无监督学习，引入了基于直接内核的自组织映射。对于监督学习，使用直接内核部分最小二乘法和（直接）内核岭回归。然后将这些结果与经典支持向量机和内核部分最小二乘法进行比较。这些方法的超参数在测试前对训练数据的验证子集进行调整。还进行了调查，最有效的预处理，使用局部，垂直，水平和二维（全局）Mahanalobis缩放，小波变换和通过过滤的变量选择。所有这三种方法类似的结果令人鼓舞，超出了受过培训的专家所实现的分类质量。因此，公开了一种用于分类心电图数据的装置和相关联的方法，包括：在使用机器学习分类变换的数据之前，将核心变换应用于从感测电磁心脏活动的传感器获取的感测数据，导致变换数据。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式